Black soil area cultivated land fertility characteristic diagnosis and evolution attribution analysis method

Abstract

The invention discloses a black soil area cultivated land fertility characteristic diagnosis and evolution attribution analysis method, and relates to the field of black land protection and remediation, and the method comprises the following steps: determining a cultivated land fertility evaluation index system through a soil moisture tachymeter and a remote sensing interpretation technology based on a cultivated land fertility related standard; according to the screening principle of the evaluation indexes, establishing an index primary selection library of the cultivated land fertility; calculating the importance of the index i through principal component analysis; the correlation balance of the index i is calculated through the distance correlation coefficient and the Gini coefficient; calculating the independence of the index i through the maximum mutual information coefficient; sorting the indexes i through an evaluation index system optimization model of the DS evidence theory, and optimizing the indexes i in combination with an index system; a cultivated land force evolution power mechanism is revealed through a factor detection module and an interaction detection module of the geographical detector; through a technical path of multi-source data fusion, multi-dimensional index optimization and spatial analysis, scientific diagnosis and dynamic attribution analysis of cultivated land fertility are realized.

Description

Technical Field

[0001] This invention relates to the field of black soil protection and restoration, and in particular to a method for diagnosing and analyzing the evolution of soil fertility characteristics in black soil regions. Background Technology

[0002] The black soil region is an important grain production base.

[0003] In existing technologies, traditional farmland fertility assessments often rely on a single data source or subjective experience. These methods often depend on limited field sampling data or historical experience models, lacking the ability to integrate multi-source data and perform dynamic monitoring. Because farmland fertility itself has significant spatial heterogeneity, temporal dynamics, and system complexity, it is difficult to comprehensively and objectively reflect the spatial heterogeneity and temporal evolution of farmland fertility using only a single data source.

[0004] In addition, traditional methods often involve long cycles, high costs, and limited coverage in data acquisition, making it impossible to achieve large-scale, high-frequency dynamic monitoring. This results in evaluation results lagging behind actual changes, making it difficult to provide effective support for precision agricultural management and timely intervention.

[0005] Therefore, a method for diagnosing and analyzing the evolution of soil fertility characteristics in black soil regions is proposed to address the above-mentioned problems. Summary of the Invention

[0006] The purpose of this invention is to provide a method for diagnosing the soil fertility characteristics and analyzing the evolution of soil fertility in black soil regions. By integrating multi-source data and screening multi-dimensional indicators, a scientific diagnosis and analysis of the evolution mechanism of soil fertility in black soil regions can be achieved.

[0007] To achieve the above objectives, this invention provides a method for diagnosing and analyzing the evolution of soil fertility characteristics in black soil regions, comprising the following steps: S1: Based on relevant standards for arable land fertility, an evaluation index system for arable land fertility is determined using soil moisture rapid testing instruments and remote sensing interpretation technology; S2: Based on the selection principles of evaluation indicators, establish a preliminary selection library of evaluation indicators for arable land fertility; S3: Calculate evaluation indicators using principal component analysis (PCA). i The importance of; S4: Calculate evaluation indicators using distance correlation coefficient and Gini coefficient. i The correlation balance; S5: Calculate the evaluation index using the maximum mutual information coefficient (MIC). i Independence; S6: Based on evaluation metrics i The importance, correlation equilibrium, and independence of the evaluation indicators are considered using the DS evidence theory-based evaluation indicator system optimization model. iRank the indicators and select the best ones based on the evaluation indicator system. i ; S7: Reveal the dynamic mechanism of farmland fertility evolution through the factor detection module and interactive detection module of the geographic detector.

[0008] Preferably, step S1 specifically includes the following steps: S11: The volumetric water content of the soil is detected at the sampling point using a soil moisture meter. The probes at different depths are replaced and the sampling points are tested repeatedly to obtain the profile information of the sampling points. S12: Record the latitude and longitude coordinates of each sampling point using a GPS positioning device; S13: Based on latitude and longitude coordinates, spatial continuous information and meteorological information of sampling points are obtained through remote sensing technology. The spatial continuous information and meteorological information are then inverted to obtain key farmland fertility parameters. S14: Construct a farmland fertility evaluation index system by combining profile information and key farmland fertility parameters.

[0009] Preferably, in step S2, the selection principles for evaluation indicators include scientificity, completeness, operability, independence, and dynamism.

[0010] Preferably, step S3 specifically includes the following steps: S31: Evaluation Indicators i The standardized evaluation index matrix X is obtained by performing standardization processing. S32: Perform eigenvalue decomposition on the evaluation index matrix X to obtain eigenvalues. l i Sum and eigenvalues l i corresponding feature vector v i ; S33: Evaluation Indicators i Projection is performed to obtain evaluation indicators. i The corresponding principal component PC i ; S34: Calculate PC for each principal component i The variance contribution rate and the top k The principal component PC i The cumulative variance contribution rate, the first k The principal component PC i The cumulative variance contribution rate is greater than 80%; S35: According to the previous k The principal component PC i The load is used to obtain each evaluation index. i The degree of commonality.

[0011] Preferably, step S4 specifically includes the following steps: S41: Confirm n target vectors j Calculate evaluation indicators i With the target vector j The distance correlation coefficient between them is used to obtain the evaluation index for each indicator. i Corresponding correlation strength vector V ; S42: Associate the strength vector V The distance correlation coefficients are sorted in ascending order; S43: Based on association strength vector V Calculate the Gini coefficient G i Gini coefficient G i The smaller the evaluation index i The higher the correlation balance, the better.

[0012] Preferably, in step S43, the Gini coefficient G i Specifically set as follows: in, This represents the sorted association strength vector. n Indicators i The quantity.

[0013] Preferably, step S5 specifically includes the following steps: S51: Calculate evaluation indicators i The pairwise MIC values ​​form a symmetric matrix M; S52: Calculate the average of the off-diagonal elements in a single row or column of a symmetric matrix M. The smaller the average, the better the evaluation index. i The higher the degree of independence.

[0014] Preferably, step S6 specifically includes the following steps: S61: For principal component PC i The variance contribution rate was normalized to obtain evidence of importance; S62: Gini coefficients G i The complementary values ​​are normalized to obtain evidence of correlation equilibrium. S63: Normalize the row average of the symmetric matrix M to obtain evidence of independence; S64: By fusing the basic probability allocations of importance evidence, relevance equilibrium evidence, and independence evidence using the Dempster combination rule of DS evidence theory, an evaluation index is obtained. i Overall trust level; S65: Evaluation indicators based on overall trust level i Sort in descending order, and prioritize evaluation indicators with a comprehensive trust level greater than 80%. i This is summarized into an optimal set of indicators, from which the best evaluation indicator is selected. i .

[0015] Preferably, step S7 specifically includes the following steps: S71: Calculate the detection power value using the factor detection module of the geographic detector, and analyze the spatial differentiation and evaluation indicators of cultivated land based on the detection power value. i Impact on spatial heterogeneity; S72: Evaluation Indicators i The matrix is ​​standardized to obtain the standardized values ​​of the matrix variables; S73: Project the standardized values ​​to obtain the projected values ​​and the variance of the projected values; S74: Calculate the correlation coefficient between the matrix variables and the projected values.

[0016] Therefore, the present invention employs the above-mentioned method for diagnosing and analyzing the evolution of arable land fertility characteristics in black soil regions, which has the following beneficial effects: (1) This scheme combines field measurements with spatial continuous information and meteorological information to achieve point-area combination and multi-scale data collection, breaking through the limitations of traditional single data sources. Through GPS positioning and remote sensing inversion technology, it achieves high-precision spatial extraction of key farmland fertility parameters. (2) This scheme proposes a three-dimensional index selection framework based on principal component analysis (PCA), distance correlation coefficient, Gini coefficient, and maximum mutual information coefficient (MIC), which systematically solves the problems of subjectivity and redundancy in index selection. (3) This scheme introduces remote sensing technology and GIS platform to realize the spatiotemporal dynamic monitoring and spatial visualization analysis of farmland fertility, which can reveal the dynamic mechanism of soil fertility evolution, have the ability to respond to the complex spatial heterogeneity of black soil area, and support regional differentiated governance strategies.

[0017] The method of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0018] Figure 1 This is a flowchart of a method for diagnosing and analyzing the evolution of soil fertility characteristics in black soil regions according to the present invention. Detailed Implementation

[0019] The method of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] Unless otherwise defined, the methodological or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0021] The terms "comprising" or "including" as used in this invention mean that the element preceding the term encompasses the element listed after the term, and do not exclude the possibility of encompassing other elements. Terms such as "inner," "outer," "upper," and "lower" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. In this invention, unless otherwise explicitly specified and limited, the term "attached" and similar terms should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can refer to a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication of two elements or the interaction relationship between two elements. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0022] Example like Figure 1 As shown, this invention provides a method for diagnosing and analyzing the evolution of soil fertility characteristics in black soil regions, comprising the following steps: S1: Based on relevant standards for arable land fertility, an evaluation index system for arable land fertility is determined using soil moisture rapid testing instruments and remote sensing interpretation technology; Step S1 specifically includes the following steps: S11: The volumetric water content of the soil is detected at the sampling point using a soil moisture meter. The probes at different depths are replaced and the sampling points are tested repeatedly to obtain the profile information of the sampling points. S12: Record the latitude and longitude coordinates of each sampling point using a GPS positioning device; S13: Based on latitude and longitude coordinates, spatial continuous information and meteorological information of sampling points are obtained through remote sensing technology. The spatial continuous information and meteorological information are then inverted to obtain key farmland fertility parameters. S14: Construct a farmland fertility evaluation index system by combining profile information and key farmland fertility parameters.

[0023] S2: Based on the selection principles of evaluation indicators, establish a preliminary selection library of evaluation indicators for arable land fertility; In step S2, the selection principles for evaluation indicators include scientificity, completeness, operability, independence, and dynamism.

[0024] S3: Calculate evaluation indicators using principal component analysis (PCA).i The importance of; Step S3 specifically includes the following steps: S31: Evaluation Indicators i The standardized evaluation index matrix X is obtained by performing standardization processing. S32: Perform eigenvalue decomposition on the evaluation index matrix X to obtain eigenvalues. l i Sum and eigenvalues l i corresponding feature vector v i ; S33: Evaluation Indicators i Projection is performed to obtain evaluation indicators. i The corresponding principal component PC i ; S34: Calculate PC for each principal component i The variance contribution rate and the top k The principal component PC i The cumulative variance contribution rate, the first k The principal component PC i The cumulative variance contribution rate is greater than 80%; S35: According to the previous k The principal component PC i The load is used to obtain each evaluation index. i The degree of commonality.

[0025] S4: Calculate evaluation indicators using distance correlation coefficient and Gini coefficient. i The correlation balance; Step S4 specifically includes the following steps: S41: Confirm n target vectors j Calculate evaluation indicators i With the target vector j The distance correlation coefficient between them is used to obtain the evaluation index for each indicator. i Corresponding correlation strength vector V ; S42: Associate the strength vector V The distance correlation coefficients are sorted in ascending order; S43: Based on association strength vector V Calculate the Gini coefficient G i Gini coefficient G i The smaller the evaluation index i The higher the correlation balance, the better.

[0026] In step S43, the Gini coefficientG i Specifically set as follows: in, This represents the sorted association strength vector. n Indicators i The quantity.

[0027] S5: Calculate the evaluation index using the maximum mutual information coefficient (MIC). i Independence; Step S5 specifically includes the following steps: S51: Calculate evaluation indicators i The pairwise MIC values ​​form a symmetric matrix M; S52: Calculate the average of the off-diagonal elements in a single row or column of a symmetric matrix M. The smaller the average, the better the evaluation index. i The higher the degree of independence.

[0028] S6: Based on evaluation metrics i The importance, correlation balance, and independence of the evaluation indicators are considered. A model for optimizing the evaluation indicator system based on the DS evidence theory is used to calculate the comprehensive relationship quantification value of the evaluation indicators. i Rank the indicators and select the best ones based on the evaluation indicator system. i ; Step S6 specifically includes the following steps: S61: For principal component PC i The variance contribution rate was normalized to obtain evidence of importance; S62: Gini coefficients G i The complementary values ​​are normalized to obtain evidence of correlation balance; S63: Normalize the row average of the symmetric matrix M to obtain evidence of independence; S64: By fusing the basic probability allocations of importance evidence, relevance equilibrium evidence, and independence evidence using the Dempster combination rule of DS evidence theory, an evaluation index is obtained. i Overall trust level; S65: Evaluation indicators based on overall trust level i Sort in descending order, and prioritize evaluation indicators with a comprehensive trust level greater than 80%. i This is summarized into an optimal set of indicators, from which the best evaluation indicator is selected. i .

[0029] S7: Reveal the dynamic mechanism of farmland fertility evolution through the factor detection module and interactive detection module of the geographic detector.

[0030] Step S7 specifically includes the following steps: S71: Calculate the detection power value using the factor detection module of the geographic detector, and analyze the spatial differentiation and evaluation indicators of cultivated land based on the detection power value. i Impact on spatial heterogeneity; S72: Evaluation Indicators i The matrix is ​​standardized to obtain the standardized values ​​of the matrix variables; S73: Project the standardized values ​​to obtain the projected values ​​and the variance of the projected values; S74: Calculate the correlation coefficient between the matrix variables and the projected values.

[0031] Therefore, this invention adopts the above-mentioned method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil areas, which solves the problems of inaccurate arable land fertility evaluation, unclear evolution mechanism, and insufficient decision support. Through the technical path of multi-source data fusion, multi-dimensional index optimization, and spatial analysis, it realizes the scientific diagnosis and dynamic attribution analysis of arable land fertility.

[0032] Finally, it should be noted that the above embodiments are only used to illustrate the method of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the method of the present invention, and these modifications or equivalent substitutions should not cause the modified method to deviate from the spirit and scope of the method of the present invention.

Claims

1. A method for diagnosing and attributing the evolution of soil fertility characteristics in black soil regions, characterized in that, Includes the following steps: S1: Based on relevant standards for arable land fertility, an evaluation index system for arable land fertility is determined using soil moisture rapid testing instruments and remote sensing interpretation technology; S2: Based on the selection principles of evaluation indicators, establish a preliminary selection library of evaluation indicators for arable land fertility; S3: Calculate evaluation indicators using principal component analysis (PCA). i The importance of; S4: Calculate evaluation indicators using distance correlation coefficient and Gini coefficient. i The correlation balance; S5: Calculate the evaluation index using the maximum mutual information coefficient (MIC). i Independence; S6: Based on evaluation metrics i The importance, correlation equilibrium, and independence of the evaluation indicators are considered using the DS evidence theory-based evaluation indicator system optimization model. i Rank the indicators and select the best ones based on the evaluation indicator system. i ; S7: Reveal the dynamic mechanism of farmland fertility evolution through the factor detection module and interactive detection module of the geographic detector.

2. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 1, characterized in that, Step S1 specifically includes the following steps: S11: The volumetric water content of the soil is detected at the sampling point using a soil moisture meter. The probes at different depths are replaced and the sampling points are tested repeatedly to obtain the profile information of the sampling points. S12: Record the latitude and longitude coordinates of each sampling point using a GPS positioning device; S13: Based on latitude and longitude coordinates, spatial continuous information and meteorological information of sampling points are obtained through remote sensing technology. The spatial continuous information and meteorological information are then inverted to obtain key farmland fertility parameters. S14: Construct a farmland fertility evaluation index system by combining profile information and key farmland fertility parameters.

3. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 1, characterized in that, In step S2, the selection principles for evaluation indicators include scientificity, completeness, operability, independence, and dynamism.

4. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 1, characterized in that, Step S3 specifically includes the following steps: S31: Evaluation Indicators i The standardized evaluation index matrix X is obtained by performing standardization processing. S32: Perform eigenvalue decomposition on the evaluation index matrix X to obtain eigenvalues. λ i Sum and eigenvalues λ i corresponding feature vector v i ; S33: Evaluation Indicators i Projection is performed to obtain evaluation indicators. i The corresponding principal component PC i ; S34: Calculate PC for each principal component i The variance contribution rate and the previous k The principal component PC i The cumulative variance contribution rate, the first k The principal component PC i The cumulative variance contribution rate is greater than 80%; S35: According to the previous k The principal component PC i The load is used to obtain each evaluation index. i The degree of commonality.

5. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 4, characterized in that, Step S4 Specifically, the following steps are included: S41: Confirm n target vectors j Calculate evaluation indicators i With the target vector j The distance correlation coefficient between them is used to obtain the evaluation index for each indicator. i Corresponding correlation strength vector V ; S42: Associate the strength vector V The distance correlation coefficients are sorted in ascending order; S43: Based on association strength vector V Calculate the Gini coefficient G i Gini coefficient G i The smaller the evaluation index i The higher the correlation balance, the better.

6. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 5, characterized in that, In step S43, the Gini coefficient G i Specifically set as follows: in, This represents the sorted association strength vector. n Indicators i The quantity.

7. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 5, characterized in that, Step S5 specifically includes the following steps: S51: Calculate evaluation indicators i The pairwise MIC values ​​form a symmetric matrix M; S52: Calculate the average of the off-diagonal elements in a single row or column of a symmetric matrix M. The smaller the average, the better the evaluation index. i The higher the degree of independence.

8. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 7, characterized in that, Step S6 specifically includes the following steps: S61: For principal component PC i The variance contribution rate was normalized to obtain evidence of importance; S62: Gini coefficients G i The complementary values ​​are normalized to obtain evidence of correlation equilibrium. S63: Normalize the row average of the symmetric matrix M to obtain evidence of independence; S64: By fusing the basic probability allocations of importance evidence, relevance equilibrium evidence, and independence evidence using the Dempster combination rule of DS evidence theory, an evaluation index is obtained. i Overall trust level; S65: Evaluation indicators based on overall trust level i Sort in descending order, and prioritize evaluation indicators with a comprehensive trust level greater than 80%. i This is summarized into an optimal set of indicators, from which the best evaluation indicator is selected. i .

9. The method for diagnosing and attributing the evolution of arable land fertility characteristics in black soil regions according to claim 1, characterized in that, Step S7 specifically includes the following steps: S71: Calculate the detection power value using the factor detection module of the geographic detector, and analyze the spatial differentiation and evaluation indicators of cultivated land based on the detection power value. i Impact on spatial heterogeneity; S72: Evaluation Indicators i The matrix is ​​standardized to obtain the standardized values ​​of the matrix variables; S73: Project the standardized values ​​to obtain the projected values ​​and the variance of the projected values; S74: Calculate the correlation coefficient between the matrix variables and the projected values.

Images